@misc{gu2025the,
author = {Gu, Yu and Fu, Jingjing and Liu, Xiaodong and Valanarasu, Jeya Maria Jose and Codella, Noel and Tan, Reuben and Wang, Jinyu and Liu, Qianchu and Jin, Ying and Zhang, Sheng and Wang, Rui and Song, Lei and Qin, Guan-Hua and Usuyama, Naoto and Wong, Cliff and Hao, Cheng and Lee, H. and Sanapathi, Praneeth and Hilado, Sarah and Jiang, Bian and Alvarez-Valle, Javier and Wei, Mu and Gao, Jianfeng and Horvitz, Eric and Lungren, Matthew P and Poon, Hoifung and Vozila, Paul},
title = {The Illusion of Readiness in Health AI},
howpublished = {arXiv},
year = {2025},
month = {September},
abstract = {Large language models have demonstrated remarkable performance in a wide range of medical benchmarks. Yet underneath the seemingly promising results lie salient growth areas, especially in cutting-edge frontiers such as multimodal reasoning. In this paper, we introduce a series of adversarial stress tests to systematically assess the robustness of flagship models and medical benchmarks. Our study reveals prevalent brittleness in the presence of simple adversarial transformations: leading systems can guess the right answer even with key inputs removed, yet may get confused by the slightest prompt alterations, while fabricating convincing yet flawed reasoning traces. Using clinician-guided rubrics, we demonstrate that popular medical benchmarks vary widely in what they truly measure. Our study reveals significant competency gaps of frontier AI in attaining real-world readiness for health applications. If we want AI to earn trust in healthcare, we must demand more than leaderboard wins and must hold AI systems accountable to ensure robustness, sound reasoning, and alignment with real medical demands.},
url = {http://approjects.co.za/?big=en-us/research/publication/the-illusion-of-readiness-in-health-ai/},
}